Automatic semantic style transfer using deep convolutional neural networks and soft masks

This paper presents an automatic image synthesis method to transfer the style of an example image to a content image. When standard neural style transfer approaches are used, the textures and colours in different semantic regions of the style image are often applied inappropriately to the content im...

Full description

Saved in:
Bibliographic Details
Published in:The Visual computer 2020-07, Vol.36 (7), p.1307-1324
Main Authors: Zhao, Hui-Huang, Rosin, Paul L., Lai, Yu-Kun, Wang, Yao-Nan
Format: Article
Language:English
Subjects:
Artificial Intelligence
Artificial neural networks
Computer Graphics
Computer Science
Fields (mathematics)
Image Processing and Computer Vision
Masks
Methods
Neural networks
Object recognition
Original Article
Semantics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents an automatic image synthesis method to transfer the style of an example image to a content image. When standard neural style transfer approaches are used, the textures and colours in different semantic regions of the style image are often applied inappropriately to the content image, ignoring its semantic layout and ruining the transfer result. In order to reduce or avoid such effects, we propose a novel method based on automatically segmenting the objects and extracting their soft semantic masks from the style and content images, in order to preserve the structure of the content image while having the style transferred. Each soft mask of the style image represents a specific part of the style image, corresponding to the soft mask of the content image with the same semantics. Both the soft masks and source images are provided as multichannel input to an augmented deep CNN framework for style transfer which incorporates a generative Markov random field model. The results on various images show that our method outperforms the most recent techniques.
ISSN:0178-2789
1432-2315
DOI:10.1007/s00371-019-01726-2